How to build, run and watch AI agents. Guides, engineering deep dives and product updates from the Rerun team.
A practical catalog of agentic design patterns: Reflection, Tool Use, Planning, and Multi-Agent, plus the five workflow patterns, a decision framework for choosing between them, and how to run them in production.
The A2A protocol is the open standard for agent-to-agent communication. Here is how it works, how it differs from MCP, and what it means for building and governing multi-agent systems in production.
Codex vs Claude Code, compared for real. Local terminal vs cloud sandbox, code quality vs autonomy, real pricing, and the orchestration layer neither CLI gives you.
AI agents can now run real accounting work, from reconciliations to month-end close. Here is what they do, where they break, and how to deploy them with approvals, audit trails, and least-privilege access.
Naive RAG retrieves once and hopes. Agentic RAG puts an agent in charge of retrieval: it plans, routes across sources, grades results, and re-retrieves until it has enough context. Here is how it works and how it beats classic RAG.
AI agent governance controls what autonomous agents can access and do, enforced at runtime, not just on paper. Here are the five pillars of a real framework and how to close the gap between policy and enforcement.
A data-backed n8n vs Zapier comparison for 2026: pricing, integrations, and AI workflows. Plus the one question both tools cannot answer, and when to reach for a governed AI agent instead.
AI agents for data analysis are easy to demo and hard to trust in production. Here is what they do, where they break, and how to run one you can actually watch and govern.
A step-by-step guide to building an AI agent: the model, tools, memory, and reasoning loop, plus the guardrails, approvals, and observability that make it production-ready.
A framework gives your agent a brain and a loop. It does not give you governance, human control, or observability. Here is how to choose an AI agent framework, and what you need around it to run one in production.
AutoGen is in maintenance mode, CrewAI went standalone. A 2026 comparison of architecture, orchestration, and production readiness, plus the governance layer both leave to you.
AI agents can now run most of the HR lifecycle, from candidate screening to onboarding to employee support. But recruiting is legally high-risk, so the deployment model matters more than the model. Here is what HR agents actually do, and how to deploy them without creating bias, privacy, and compliance exposure.
© 2026 Rerun. All rights reserved.
